Responding to a spoken command in a communication session

Abstract

A method includes, during a teleconference between a first audio input/output device and a second audio input/output device, receiving, at an analysis and response device, a signal indicating a spoken command, the spoken command associated with a command mode. The method further includes, in response to receiving the signal, generating, at the device, a reply message based on the spoken command, the reply message to be output to one or more devices selected based on the command mode. The one or more devices includes the first audio input/output device, the second audio input/output device, or a combination thereof.

We claim: 
     
       1. A method of responding to spoken commands in a communication session, the method comprising:
 receiving a first signal from a first device during a communication session between the first device and a second device, the first signal indicating a wake up message including a wake up element and a command element; 
 selecting a chosen command mode of a plurality of command modes based on the command element; 
 receiving a second signal indicating a spoken command, the spoken command associated with the chosen command mode; 
 processing the spoken command using a natural language process module to detect data corresponding to the spoken command; and 
 performing an action based on the spoken command while maintaining the communication session between the first device and the second device. 
 
     
     
       2. The method of  claim 1 , wherein the plurality of command modes includes a local mode and a broadcast mode. 
     
     
       3. The method of  claim 1 , wherein the data detected by the natural language process module includes communication session context, content of the spoken command, information identifying a meeting object, or any combination thereof. 
     
     
       4. The method of  claim 3 , wherein the meeting object includes a participant in the communication session, a list of user profiles, a first list of locations, a second list of devices, a third list of supported spoken commands, or any combination thereof. 
     
     
       5. The method of  claim 1 , wherein the spoken command includes a request for information, a media content item, to control a part of the communication session, to control the first device in the communication session, to control the second device in the communication session, or any combination thereof. 
     
     
       6. The method of  claim 5 , wherein the request to control the part of the communication session includes requesting to connect to a third device. 
     
     
       7. The method of  claim 5 , wherein the request to control the second device includes a request to activate the second device, a request to adjust a setting of the second device, or both. 
     
     
       8. The method of  claim 1 , wherein the action includes at least one of:
 (i) creating a meeting summary associated with the communication session; 
 (ii) requesting weather information for a location from a weather service; 
 (iii) controlling a lighting device in the communication session; and 
 (iv) determining if a user who created the spoken command is authorized to initiate the spoken command; and 
 (v) displaying media content on a graphical user interface of the first device based on a keyword in the spoken command. 
 
     
     
       9. An apparatus comprising:
 a processor; and 
 a memory storing instructions that, when executed by the processor, cause the processor to:
 receive a first signal from a first device during a communication session between the first device and a second device, the first signal indicating a wake up message including a wake up element and a command element; 
 select a chosen command mode of a plurality of command modes based on the command element; 
 receive a second signal indicating a spoken command, the spoken command associated with the chosen command mode; 
 process the spoken command using a natural language process module to detect data corresponding to the spoken command; and 
 perform an action based on the spoken command while maintaining the communication session between the first device and the second device. 
 
 
     
     
       10. The apparatus of  claim 9 , wherein the apparatus further includes a first controller module that inserts the data detected by the natural language process module into a first output stream between the first device and the second device. 
     
     
       11. The apparatus of  claim 9 , wherein the data detected by the natural language process module includes communication session context, content of the spoken command, information identifying a meeting object, or any combination thereof. 
     
     
       12. The apparatus of  claim 9 , wherein the spoken command includes a request for information, a media content item, to control a part of the communication session, to control the second device in the communication session, or any combination thereof. 
     
     
       13. The apparatus of  claim 12 , wherein the request to control the part of the communication session includes a request to connect to a third device. 
     
     
       14. The apparatus of  claim 12 , wherein the request to control the second device includes a request to activate the second device, a request to adjust a setting of the second device, or both. 
     
     
       15. The apparatus of  claim 9 , wherein the action includes at least one of to:
 (i) generate a meeting summary associated with the communication session; 
 (ii) request weather information for a location from a weather service; 
 (iii) control a lighting device in the communication session; and 
 (iv) determine if a user who created the spoken command is authorized to initiate the spoken command; and 
 (v) display media content on a graphical user interface of the first device based on a keyword in the spoken command. 
 
     
     
       16. A non-transitory computer-readable medium containing instructions that when executed cause a processor to:
 receive a first signal from a first device during a communication session between the first device and a second device, the first signal indicating a wake up message including a wake up element and a command element; 
 select a chosen command mode of a plurality of command modes based on the command element; 
 receive a second signal indicating a spoken command, the spoken command associated with the chosen command mode; 
 process the spoken command using a natural language process module to detect data corresponding to the spoken command; and 
 perform an action based on the spoken command while maintaining the communication session between the first device and the second device. 
 
     
     
       17. The non-transitory computer-readable medium of  claim 16 , wherein the spoken command includes a request for information, a media content item, to control a part of the communication session, to control the second device in the communication session, or any combination thereof. 
     
     
       18. The non-transitory computer-readable medium of  claim 17 , wherein the request to control the part of the communication session includes a request to connect to a third audio device. 
     
     
       19. The non-transitory computer-readable medium of  claim 17 , wherein the request to control the second device includes a request to activate the second device, a request to adjust a setting of the second device, or both. 
     
     
       20. The non-transitory computer-readable medium of  claim 16 , wherein the action includes at least one of to:
   1  create a meeting summary associated with the communication session; 
 (ii) request weather information for a location from a weather service; 
 (iii) control a lighting device in the communication session; and 
 (iv) determine if a user who created the spoken command is authorized to initiate the spoken command; and 
 (v) display media content on a graphical user interface of the first device based on a keyword in the spoken command.